跳转到主要内容

Qwen3 VL 8B Instruct

AlibabaQwen开源权重Apache 2.0 · 商用许可

描述

Qwen3-VL is a large multimodal model that unifies vision, language, and reasoning to achieve human-level perception and cognition across text, images, and video. Built on a 235B-parameter architecture, it integrates early joint training of visual and textual modalities for strong language grounding. The model supports up to a 1 million-token context window and excels at visual understanding, spatial reasoning, long video comprehension, and tool-based interaction. It can generate code from images, perform precise 2D/3D object grounding, and operate digital interfaces like a visual agent. The “Instruct” version rivals Gemini 2.5 Pro in perception benchmarks, while the “Thinking” version leads in multimodal reasoning and STEM tasks. With multilingual OCR, creative writing, and fine-grained scene interpretation, Qwen3-VL establishes a new open-source frontier for integrated vision-language intelligence.

发布日期
2025-10-14
参数规模
9.0B
上下文长度
262K
支持模态
image, text, video

能力雷达图

80
general
0
coding
60
reasoning
34
science估算
70
agents
100
multimodal

缺少专门科学评测时,Science 由 LLM Stats 科学得分或推理能力估算。

排行榜排名

领域#排名分数来源
多模态榜126
34.0
LS

基准测试分数 (LLM Stats)

(LLM Stats (zeroeval))

Chat

MM-MT-Bench7.70 / 100自报
IFEvalGoogle Research (2023)83.7%自报
Multi-IF75.1%自报

General

MMLU80.7%自报
MLVU-M78.1%自报
Include67.0%自报
BFCL-v366.3%自报

Language

MMLU-Redux84.9%自报
MMLU-Pro71.6%自报
MMLU-ProX65.4%自报

Math

MathVista-Mini77.2%自报
LiveBench 2024112562.0%自报
MathVision53.9%自报
AIME 202545.9%自报
HMMT2532.5%自报
PolyMATH30.4%自报

Multimodal

Video-MME71.4%自报
VideoMMMU65.3%自报
OSWorld33.9%自报

Reasoning

CharXiv-D83.0%自报
CharXiv-R46.4%自报
SuperGPQA44.5%自报
LiveCodeBench v639.3%自报

Video

CharadesSTA56.0%自报

Vision

DocVQAtest96.1%自报
ScreenSpot94.4%自报
OCRBench89.6%自报
AI2D85.7%自报
MMBench-V1.185.0%自报
InfoVQAtest83.1%自报
CC-OCR79.9%自报
RealWorldQA71.5%自报
MMStar70.9%自报
MMMU (val)69.6%自报
BLINK69.1%自报
MVBench68.7%自报
OCRBench-V2 (en)65.4%自报
MuirBench64.4%自报
OCRBench-V2 (zh)61.2%自报
Hallusion Bench61.1%自报
LVBench58.0%自报
MMMU-Pro55.9%自报
ScreenSpot Pro54.6%自报
ERQA45.8%自报
ODinW44.7%自报

Writing

WritingBench83.1%自报

AA 评测指数

(Artificial Analysis)

暂无 AA 评测数据

LLM Stats 分类评分

(LLM Stats (zeroeval))
Chat
3
Communication
3
Multimodal
100
Instruction Following
80
Structured Output
80
General
80
Creativity
80
Text-to-image
80
Writing
80
Image To Text
70
Language
70
Legal
70
Finance
70
Grounding
70
Healthcare
70
3d
70
Tool Calling
70
Vision
70
Long Context
60
Math
60
Reasoning
60
Spatial Reasoning
60
Video
60
Agents
50
Physics
40
Chemistry
40
Economics
40

定价

输入价格$0.25 / 1M tokens
输出价格$0.75 / 1M tokens
混合价格(3:1)$0.375 / 1M tokens
缓存读取价格$0.12 / 1M tokens

速度

暂无速度数据

供应商价格排行

供应商价格排行

1 个供应商

供应商输入输出
1Alibaba主要
$0.25
$0.75

比较该模型在不同 API 供应商之间的定价。

外部链接